INDEX

Explanations

numeric data and statistics related to test results, errors, and demographics

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

WillAppear

-0.48

ArgumentParser

-0.47

RRect

-0.45

 Савезне

-0.45

PutMapping

-0.44

 JScrollPane

-0.42

setContentView

-0.41

GA

-0.38

Ga

-0.38

 StatefulWidget

-0.38

POSITIVE LOGITS

ValueStyle

0.65

0.51

 koszulka

0.47

 pegatina

0.45

 miniaturka

0.44

 žá

0.44

enumi

0.43

 coklat

0.43

iprot

0.43

elfare

0.43

Activations Density 0.565%

numeric data and statistics related to test results, errors, and demographics

No Comments

No Known Activations